PPTX/ODP: embedded video and audio are not represented in the document #4740

"""Reproduce: PPTX footer/date/slide-number placeholders arrive as body text, and an embedded video is ignored.

Usage: repro_pptx_footer_video.py <path-to-a-short-mp4>
"""

import sys
from importlib.metadata import version
from io import BytesIO

from docling.datamodel.base_models import InputFormat
from docling.document_converter import DocumentConverter
from docling_core.types.doc import ContentLayer, TextItem
from docling_core.types.io import DocumentStream
from lxml import etree
from pptx import Presentation
from pptx.util import Inches


P = "http://schemas.openxmlformats.org/presentationml/2006/main"
A = "http://schemas.openxmlformats.org/drawingml/2006/main"


def placeholder(ph_type: str, idx: int, text: str) -> etree._Element:
    return etree.fromstring(
        f'<p:sp xmlns:p="{P}" xmlns:a="{A}"><p:nvSpPr><p:cNvPr id="{10 + idx}" name="{ph_type} {idx}"/>'
        f'<p:cNvSpPr><a:spLocks noGrp="1"/></p:cNvSpPr><p:nvPr><p:ph type="{ph_type}" idx="{idx}"/></p:nvPr>'
        f"</p:nvSpPr><p:spPr/><p:txBody><a:bodyPr/><a:p><a:r><a:t>{text}</a:t></a:r></a:p></p:txBody></p:sp>"
    )


def build(video: str) -> BytesIO:
    prs = Presentation()
    slide = prs.slides.add_slide(prs.slide_layouts[6])
    slide.shapes.add_textbox(Inches(1), Inches(1), Inches(6), Inches(1)).text_frame.text = "Slide body text"
    tree = slide.shapes._spTree
    tree.append(placeholder("ftr", 11, "Company confidential footer"))
    tree.append(placeholder("dt", 10, "10 October 2026"))
    tree.append(placeholder("sldNum", 12, "1"))
    slide.shapes.add_movie(video, Inches(1), Inches(3), Inches(4), Inches(2.25), mime_type="video/mp4")
    buf = BytesIO()
    prs.save(buf)
    buf.seek(0)
    return buf


result = DocumentConverter(allowed_formats=[InputFormat.PPTX]).convert(
    DocumentStream(name="repro.pptx", stream=build(sys.argv[1]))
)
print(f"docling {version('docling')}, docling-core {version('docling-core')}, python {sys.version.split()[0]}")
for item, _ in result.document.iterate_items(included_content_layers=set(ContentLayer)):
    label = item.label.value if hasattr(item, "label") else type(item).__name__
    text = item.text if isinstance(item, TextItem) else ""
    print(f"{label}: {text!r} [{item.content_layer.value}]")